Domain independent static video summarization using sparse autoencoders and K-means clustering

Mohan, Jesna; Nair, Madhu S.

doi:10.3233/jifs-169906

Cited by 10 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 9 shows the result in scenario 2. We see that DFCM performs better than the other two clustering techniques (i.e., FCM, K-means) [32]. The proposed architecture achieves outstanding forecasting quality with less biased outcomes in all situations.…”

Section: Robustness Examinationmentioning

confidence: 80%

An emerging online business decision making architecture in a dynamic economic environment

Lin

Chang

Hsu

2019

IFS

View full text Add to dashboard Cite

It is widely acknowledged that a corporate's profitability that decreases dramatically not only threatens both potential and current investors, but also can freeze stock market transactions as well as deteriorate the flow of economic resources. However, far too little attention has been paid to this issue, which also has been deemed as a main trigger for a financial crisis. To confront this problem, a decision support system can be built up to evaluate a corporate's operating performance. Thus, this study introduces a novel architecture for forecasting the online operating performance of a firm when entering data at different time intervals. The introduced architecture is grounded on multiple data envelopment analysis specifications, dynamic fuzzy c-means (DFCM), and extreme support vector machine (ESVM). Because obtaining a comprehensible architecture is essential for achieving high accuracy in today's knowledge-based economy, this study advances the opaque nature of the introduced architecture and extracts the inherent knowledge to represent it in a transparent, human-readable format. The decision logics can be judged or examined by users, which will increase the acceptance rate of the architecture as well as enhance its practical application. Our built-up architecture, tested by real cases, is a promising alternative for financial performance forecasting.

show abstract

Section: Robustness Examinationmentioning

confidence: 80%

An emerging online business decision making architecture in a dynamic economic environment

Lin

Chang

Hsu

2019

IFS

View full text Add to dashboard Cite

show abstract

“…In addition, the Calinski-Harabasz index (CH index) was used enabling users to select keyframes without any computational cost. In [61] SAEKMVS (Sparse AutoEncoders and K-Means clustering VS) was presented where VS was achieved by the Dual Layer Loopy Belief Propagation Network (DLBPN) and a k-means clustering. In KEGC (Keyframe Extraction via Graph Clustering) [62] was introduced a VS approach using graph clustering after local features were extracted from video frames using the LBP descriptor and points of interest using the SIFT algorithm.…”

Section: Video Summarization Methods Using the Ov Datasetmentioning

confidence: 99%

SalSum: Saliency-based Video Summarization using Generative Adversarial Networks

Pantazis,

Dimas,

Iakovidis

2020

Preprint

View full text Add to dashboard Cite

The huge amount of video data produced daily by camera-based systems, such as surveilance, medical and telecommunication systems, emerges the need for effective video summarization (VS) methods. These methods should be capable of creating an overview of the video content. In this paper, we propose a novel VS method based on a Generative Adversarial Network (GAN) model pre-trained with human eye fixations. The main contribution of the proposed method is that it can provide perceptually compatible video summaries by combining both perceived color and spatiotemporal visual attention cues in a unsupervised scheme. Several fusion approaches are considered for robustness under uncertainty, and personalization. The proposed method is evaluated in comparison to state-of-the-art VS approaches on the benchmark dataset VSUMM. The experimental results conclude that SalSum outperforms the state-of-the-art approaches by providing the highest f-measure score on the VSUMM benchmark.

show abstract

“…The first 23 papers are related to image and signal processing. In [1], the authors address the challenge of extracting interesting videos from huge video repositories. They present a novel method for domain-independent static video summarization that captures essential content of a video.…”

mentioning

confidence: 99%

Soft computing and intelligent systems: techniques and applications

Thampi

El-Alfy

2019

IFS

View full text Add to dashboard Cite

Domain independent static video summarization using sparse autoencoders and K-means clustering

Cited by 10 publications

References 14 publications

An emerging online business decision making architecture in a dynamic economic environment

An emerging online business decision making architecture in a dynamic economic environment

SalSum: Saliency-based Video Summarization using Generative Adversarial Networks

Soft computing and intelligent systems: techniques and applications

Contact Info

Product

Resources

About